© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17768
    Prev
    Next
    INDEX
    Explanations

    documentation, posts, or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĩĢåĮĸ
    -0.27
    alent
    -0.27
    Contained
    -0.27
    ModelError
    -0.25
     gratuito
    -0.25
    å¾ĹæĦı
    -0.25
    ajan
    -0.24
    PrivateKey
    -0.24
     privateKey
    -0.23
    [end
    -0.23
    POSITIVE LOGITS
    istencia
    0.31
    æĸ½
    0.28
     woo
    0.27
    ist
    0.27
     whisk
    0.25
    stre
    0.25
    ource
    0.25
    æĬ¥
    0.24
    ateg
    0.24
    z
    0.24
    Activations Density 0.142%

    No Known Activations